Open Access. Powered by Scholars. Published by Universities.®

Artificial Intelligence and Robotics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Air Force Institute of Technology

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 91 - 120 of 137

Full-Text Articles in Artificial Intelligence and Robotics

Evolutionary Artificial Neural Network Weight Tuning To Optimize Decision Making For An Abstract Game, Corey M. Miller Mar 2010

Evolutionary Artificial Neural Network Weight Tuning To Optimize Decision Making For An Abstract Game, Corey M. Miller

Theses and Dissertations

Abstract strategy games present a deterministic perfect information environment with which to test the strategic capabilities of artificial intelligence systems. With no unknowns or random elements, only the competitors’ performances impact the results. This thesis takes one such game, Lines of Action, and attempts to develop a competitive heuristic. Due to the complexity of Lines of Action, artificial neural networks are utilized to model the relative values of board states. An application, pLoGANN (Parallel Lines of Action with Genetic Algorithm and Neural Networks), is developed to train the weights of this neural network by implementing a genetic algorithm over a …

Go to article

Unified Behavior Framework For Reactive Robot Control, Brian G. Woolley, Gilbert L. Peterson Jul 2009

Unified Behavior Framework For Reactive Robot Control, Brian G. Woolley, Gilbert L. Peterson

Faculty Publications

Behavior-based systems form the basis of autonomous control for many robots. In this article, we demonstrate that a single software framework can be used to represent many existing behavior based approaches. The unified behavior framework presented, incorporates the critical ideas and concepts of the existing reactive controllers. Additionally, the modular design of the behavior framework: (1) simplifies development and testing; (2) promotes the reuse of code; (3) supports designs that scale easily into large hierarchies while restricting code complexity; and (4) allows the behavior based system developer the freedom to use the behavior system they feel will function the best. …

Go to article

A Secure Group Communication Architecture For Autonomous Unmanned Aerial Vehicles, Adrian N. Phillips, Barry E. Mullins, Richard Raines, Rusty O. Baldwin Aug 2008

A Secure Group Communication Architecture For Autonomous Unmanned Aerial Vehicles, Adrian N. Phillips, Barry E. Mullins, Richard Raines, Rusty O. Baldwin

Faculty Publications

This paper investigates the application of a secure group communication architecture to a swarm of autonomous unmanned aerial vehicles (UAVs). A multicast secure group communication architecture for the low earth orbit (LEO) satellite environment is evaluated to determine if it can be effectively adapted to a swarm of UAVs and provide secure, scalable, and efficient communications. The performance of the proposed security architecture is evaluated with two other commonly used architectures using a discrete event computer simulation developed using MATLAB. Performance is evaluated in terms of the scalability and efficiency of the group key distribution and management scheme when the …

Go to article

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries, Gilbert L. Peterson Jul 2008

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries, Gilbert L. Peterson

Faculty Publications

This paper merges hierarchical reinforcement learning (HRL) with ant colony optimization (ACO) to produce a HRL ACO algorithm capable of generating solutions for large domains. This paper describes two specific implementations of the new algorithm: the first a modification to Dietterich’s MAXQ-Q HRL algorithm, the second a hierarchical ant colony system algorithm. These implementations generate faster results, with little to no significant change in the quality of solutions for the tested problem domains. The application of ACO to the MAXQ-Q algorithm replaces the reinforcement learning, Q-learning, with the modified ant colony optimization method, Ant-Q. This algorithm, MAXQ-AntQ, converges to solutions …

Go to article

Behavior-Based Power Management In Autonomous Mobile Robots, Charles A. Fetzek Mar 2008

Behavior-Based Power Management In Autonomous Mobile Robots, Charles A. Fetzek

Theses and Dissertations

Current attempts to prolong the life of a robot on a single battery charge focus on lowering the operating frequency of the onboard hardware, or allowing devices to go to sleep during idle states. These techniques have much overhead and do not come built in to the underlying robotic architecture. In this thesis, battery life is greatly extended through development of a behavior-based power management system, including a Markov decision process power planner, thereby allowing future robots increased time to operate and loiter in their required domain. Behavior-based power management examines sensors needed by the currently active behavior set and …

Go to article

Dynamic Behavior Sequencing In A Hybrid Robot Architecture, Jeffrey P. Duffy Mar 2008

Dynamic Behavior Sequencing In A Hybrid Robot Architecture, Jeffrey P. Duffy

Theses and Dissertations

Hybrid robot control architectures separate plans, coordination, and actions into separate processing layers to provide deliberative and reactive functionality. This approach promotes more complex systems that perform well in goal-oriented and dynamic environments. In various architectures, the connections and contents of the functional layers are tightly coupled so system updates and changes require major changes throughout the system. This work proposes an abstract behavior representation, a dynamic behavior hierarchy generation algorithm, and an architecture design to reduce this major change incorporation process. The behavior representation provides an abstract interface for loose coupling of behavior planning and execution components. The hierarchy …

Go to article

Exploitation Of Self Organization In Uav Swarms For Optimization In Combat Environments, Dustin J. Nowak Mar 2008

Exploitation Of Self Organization In Uav Swarms For Optimization In Combat Environments, Dustin J. Nowak

Theses and Dissertations

This investigation focuses primarily on the development of effective target engagement for unmanned aerial vehicle (UAV) swarms using autonomous self-organized cooperative control. This development required the design of a new abstract UAV swarm control model which flows from an abstract Markov structure, a Partially Observable Markov Decision Process. Self-organization features, bio-inspired attack concepts, evolutionary computation (multi-objective genetic algorithms, differential evolution), and feedback from environmental awareness are instantiated within this model. The associated decomposition technique focuses on the iterative deconstruction of the problem domain state and dynamically building-up of self organizational rules as related to the problem domain environment. Resulting emergent …

Go to article

Conceptual Study Of Rotary-Wing Microrobotics, Kelson D. Chabak Mar 2008

Conceptual Study Of Rotary-Wing Microrobotics, Kelson D. Chabak

Theses and Dissertations

This thesis presents a novel rotary-wing micro-electro-mechanical systems (MEMS) robot design. Two MEMS wing designs were designed, fabricated and tested including one that possesses features conducive to insect level aerodynamics. Two methods for fabricating an angled wing were also attempted with photoresist and CrystalBond™ to create an angle of attack. One particular design consisted of the wing designs mounted on a gear which are driven by MEMS actuators. MEMS comb drive actuators were analyzed, simulated and tested as a feasible drive system. The comb drive resonators were also designed orthogonally which successfully rotated a gear without wings. With wings attached …

Go to article

A Secure Group Communication Architecture For A Swarm Of Autonomous Unmanned Aerial Vehicles, Adrian N. Phillips Mar 2008

A Secure Group Communication Architecture For A Swarm Of Autonomous Unmanned Aerial Vehicles, Adrian N. Phillips

Theses and Dissertations

This thesis investigates the application of a secure group communication architecture to a swarm of autonomous unmanned aerial vehicles (UAVs). A multicast secure group communication architecture for the low earth orbit (LEO) satellite environment is evaluated to determine if it can be effectively adapted to a swarm of UAVs and provide secure, scalable, and efficient communications. The performance of the proposed security architecture is evaluated with two other commonly used architectures using a discrete event computer simulation developed using MatLab. Performance is evaluated in terms of the scalability and efficiency of the group key distribution and management scheme when the …

Go to article

Ant Clustering With Locally Weighting Ant Perception And Diversified Memory, Gilbert L. Peterson, Christopher B. Mayer, Thomas L. Kubler Mar 2008

Ant Clustering With Locally Weighting Ant Perception And Diversified Memory, Gilbert L. Peterson, Christopher B. Mayer, Thomas L. Kubler

Faculty Publications

Ant clustering algorithms are a robust and flexible tool for clustering data that have produced some promising results. This paper introduces two improvements that can be incorporated into any ant clustering algorithm: kernel function similarity weights and a similarity memory model replacement scheme. A kernel function weights objects within an ant’s neighborhood according to the object distance and provides an alternate interpretation of the similarity of objects in an ant’s neighborhood. Ants can hill-climb the kernel gradients as they look for a suitable place to drop a carried object. The similarity memory model equips ants with a small memory consisting …

Go to article

A Unified Framework For Solving Multiagent Task Assignment Problems, Kevin Cousin Dec 2007

A Unified Framework For Solving Multiagent Task Assignment Problems, Kevin Cousin

Theses and Dissertations

Multiagent task assignment problem descriptors do not fully represent the complex interactions in a multiagent domain, and algorithmic solutions vary widely depending on how the domain is represented. This issue is compounded as related research fields contain descriptors that similarly describe multiagent task assignment problems, including complex domain interactions, but generally do not provide the mechanisms needed to solve the multiagent aspect of task assignment. This research presents a unified approach to representing and solving the multiagent task assignment problem for complex problem domains. Ideas central to multiagent task allocation, project scheduling, constraint satisfaction, and coalition formation are combined to …

Go to article

A Hybrid Multi-Robot Control Architecture, Daylond J. Hooper Dec 2007

A Hybrid Multi-Robot Control Architecture, Daylond J. Hooper

Theses and Dissertations

Multi-robot systems provide system redundancy and enhanced capability versus single robot systems. Implementations of these systems are varied, each with specific design approaches geared towards an application domain. Some traditional single robot control architectures have been expanded for multi-robot systems, but these expansions predominantly focus on the addition of communication capabilities. Both design approaches are application specific and limit the generalizability of the system. This work presents a redesign of a common single robot architecture in order to provide a more sophisticated multi-robot system. The single robot architecture chosen for application is the Three Layer Architecture (TLA). The primary strength …

Go to article

Parallelization Of Ant Colony Optimization Via Area Of Expertise Learning, Adrian A. De Freitas Sep 2007

Parallelization Of Ant Colony Optimization Via Area Of Expertise Learning, Adrian A. De Freitas

Theses and Dissertations

Ant colony optimization algorithms have long been touted as providing an effective and efficient means of generating high quality solutions to NP-hard optimization problems. Unfortunately, while the structure of the algorithm is easy to parallelize, the nature and amount of communication required for parallel execution has meant that parallel implementations developed suffer from decreased solution quality, slower runtime performance, or both. This thesis explores a new strategy for ant colony parallelization that involves Area of Expertise (AOE) learning. The AOE concept is based on the idea that individual agents tend to gain knowledge of different areas of the search space …

Go to article

Multi-Objective Optimization For Speed And Stability Of A Sony Aibo Gait, Christopher A. Patterson Sep 2007

Multi-Objective Optimization For Speed And Stability Of A Sony Aibo Gait, Christopher A. Patterson

Theses and Dissertations

Locomotion is a fundamental facet of mobile robotics that many higher level aspects rely on. However, this is not a simple problem for legged robots with many degrees of freedom. For this reason, machine learning techniques have been applied to the domain. Although impressive results have been achieved, there remains a fundamental problem with using most machine learning methods. The learning algorithms usually require a large dataset which is prohibitively hard to collect on an actual robot. Further, learning in simulation has had limited success transitioning to the real world. Also, many learning algorithms optimize for a single fitness function, …

Go to article

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries Sep 2007

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries

Theses and Dissertations

This research merges the hierarchical reinforcement learning (HRL) domain and the ant colony optimization (ACO) domain. The merger produces a HRL ACO algorithm capable of generating solutions for both domains. This research also provides two specific implementations of the new algorithm: the first a modification to Dietterich's MAXQ-Q HRL algorithm, the second a hierarchical ACO algorithm. These implementations generate faster results, with little to no significant change in the quality of solutions for the tested problem domains. The application of ACO to the MAXQ-Q algorithm replaces the reinforcement learning, Q-learning and SARSA, with the modified ant colony optimization method, Ant-Q. …

Go to article

An Artificial Immune System-Inspired Multiobjective Evolutionary Algorithm With Application To The Detection Of Distributed Computer Network Intrusions, Charles R. Haag, Gary B. Lamont, Paul D. L. Williams, Gilbert L. Peterson Jul 2007

An Artificial Immune System-Inspired Multiobjective Evolutionary Algorithm With Application To The Detection Of Distributed Computer Network Intrusions, Charles R. Haag, Gary B. Lamont, Paul D. L. Williams, Gilbert L. Peterson

Faculty Publications

Today's signature-based intrusion detection systems are reactive in nature and storage-limited. Their operation depends upon catching an instance of an intrusion or virus and encoding it into a signature that is stored in its anomaly database, providing a window of vulnerability to computer systems during this time. Further, the maximum size of an Internet Protocol-based message requires the database to be huge in order to maintain possible signature combinations. In order to tighten this response cycle within storage constraints, this paper presents an innovative Artificial Immune System-inspired Multiobjective Evolutionary Algorithm. This distributed intrusion detection system (IDS) is intended to measure …

Go to article

Genetic Evolution Of Hierarchical Behavior Structures, Brian G. Woolley, Gilbert L. Peterson Jul 2007

Genetic Evolution Of Hierarchical Behavior Structures, Brian G. Woolley, Gilbert L. Peterson

Faculty Publications

The development of coherent and dynamic behaviors for mobile robots is an exceedingly complex endeavor ruled by task objectives, environmental dynamics and the interactions within the behavior structure. This paper discusses the use of genetic programming techniques and the unified behavior framework to develop effective control hierarchies using interchangeable behaviors and arbitration components. Given the number of possible variations provided by the framework, evolutionary programming is used to evolve the overall behavior design. Competitive evolution of the behavior population incrementally develops feasible solutions for the domain through competitive ranking. By developing and implementing many simple behaviors independently and then evolving …

Go to article

Wide Area Search And Engagement Simulation Validation, Michael J. Marlin Mar 2007

Wide Area Search And Engagement Simulation Validation, Michael J. Marlin

Theses and Dissertations

As unmanned aerial vehicles (UAVs) increase in capability, the ability to refuel them in the air is becoming more critical. Aerial refueling will extend the range, shorten the response times, and extend loiter time of UAVs. Executing aerial refueling autonomously will reduce the command and control, logistics, and training efforts associated with fielding UAV systems. Currently, the Air Force Research Lab is researching the various technologies required to conduct automated aerial refueling (AAR). One of the required technologies is the ability to autonomously rendezvous with the tanker. The goal of this research is to determine the control required to fly …

Go to article

Performance Evaluation Of Ad Hoc Routing In A Swarm Of Autonomous Aerial Vehicles, Matthew T. Hyland Mar 2007

Performance Evaluation Of Ad Hoc Routing In A Swarm Of Autonomous Aerial Vehicles, Matthew T. Hyland

Theses and Dissertations

This thesis investigates the performance of three mobile ad hoc routing protocols in the context of a swarm of autonomous unmanned aerial vehicles (UAVs). It is proposed that a wireless network of nodes having an average of 5.1774 log n neighbors, where n is the total number of nodes in the network, has a high probability of having no partitions. By decreasing transmission range while ensuring network connectivity, and implementing multi-hop routing between nodes, spatial multiplexing is exploited whereby multiple pairs of nodes simultaneously transmit on the same channel. The proposal is evaluated using the Greedy Perimeter Stateless Routing (GPSR), …

Go to article

Multi-Robot Fastslam For Large Domains, Choyong G. Koperski Mar 2007

Multi-Robot Fastslam For Large Domains, Choyong G. Koperski

Theses and Dissertations

For a robot to build a map of its surrounding area, it must have accurate position information within the area, and to obtain accurate position information within the area, the robot needs to have an accurate map of the area. This circular problem is the Simultaneous Localization and Mapping (SLAM) problem. An efficient algorithm to solve it is FastSLAM, which is based on the Rao-Blackwellized particle filter. FastSLAM solves the SLAM problem for single-robot mapping using particles to represent the posterior of the robot pose and the map. Each particle of the filter possesses its own global map which is …

Go to article

Fuzzy State Aggregation And Off-Policy Reinforcement Learning For Stochastic Environments, Dean C. Wardell, Gilbert L. Peterson May 2006

Fuzzy State Aggregation And Off-Policy Reinforcement Learning For Stochastic Environments, Dean C. Wardell, Gilbert L. Peterson

Faculty Publications

Reinforcement learning is one of the more attractive machine learning technologies, due to its unsupervised learning structure and ability to continually learn even as the environment it is operating in changes. This ability to learn in an unsupervised manner in a changing environment is applicable in complex domains through the use of function approximation of the domain’s policy. The function approximation presented here is that of fuzzy state aggregation. This article presents the use of fuzzy state aggregation with the current policy hill climbing methods of Win or Lose Fast (WoLF) and policy-dynamics based WoLF (PD-WoLF), exceeding the learning rate …

Go to article

Application Of Fuzzy State Aggregation And Policy Hill Climbing To Multi-Agent Systems In Stochastic Environments, Dean C. Wardell Mar 2006

Application Of Fuzzy State Aggregation And Policy Hill Climbing To Multi-Agent Systems In Stochastic Environments, Dean C. Wardell

Theses and Dissertations

Reinforcement learning is one of the more attractive machine learning technologies, due to its unsupervised learning structure and ability to continually even as the operating environment changes. Applying this learning to multiple cooperative software agents (a multi-agent system) not only allows each individual agent to learn from its own experience, but also opens up the opportunity for the individual agents to learn from the other agents in the system, thus accelerating the rate of learning. This research presents the novel use of fuzzy state aggregation, as the means of function approximation, combined with the policy hill climbing methods of Win …

Go to article

A Monocular Vision Based Approach To Flocking, Brian Kirchner Mar 2006

A Monocular Vision Based Approach To Flocking, Brian Kirchner

Theses and Dissertations

Flocking is seen in nature as a means for self protection, more efficient foraging, and other search behaviors. Although much research has been done regarding the application of this principle to autonomous vehicles, the majority of the research has relied on GPS information, broadcast communication, an omniscient central controller, or some other form of "global" knowledge. This approach, while effective, has serious drawbacks, especially regarding stealth, reliability, and biological grounding. This research effort uses three Pioneer P2-AT8 robots to achieve flocking behavior without the use of global knowledge. The sensory inputs are limited to two cameras, offset such that the …

Go to article

Cooperative Reinforcement Learning Using An Expert-Measuring Weighted Strategy With Wolf, Kevin Cousin, Gilbert L. Peterson Sep 2005

Cooperative Reinforcement Learning Using An Expert-Measuring Weighted Strategy With Wolf, Kevin Cousin, Gilbert L. Peterson

Faculty Publications

Gradient descent learning algorithms have proven effective in solving mixed strategy games. The policy hill climbing (PHC) variants of WoLF (Win or Learn Fast) and PDWoLF (Policy Dynamics based WoLF) have both shown rapid convergence to equilibrium solutions by increasing the accuracy of their gradient parameters over standard Q-learning. Likewise, cooperative learning techniques using weighted strategy sharing (WSS) and expertness measurements improve agent performance when multiple agents are solving a common goal. By combining these cooperative techniques with fast gradient descent learning, an agent’s performance converges to a solution at an even faster rate. This statement is verified in a …

Go to article

Cognitive Robot Mapping With Polylines And An Absolute Space Representation, Kennard R. Laviers, Gilbert L. Peterson Apr 2004

Cognitive Robot Mapping With Polylines And An Absolute Space Representation, Kennard R. Laviers, Gilbert L. Peterson

Faculty Publications

Robot mapping even today is one of the most challenging problems in robot programming. Most successful methods use some form of occupancy grid to represent a mapped region. This approach becomes problematic if the robot is mapping a large environment, the map quickly becomes too large for processing and storage. Rather than storing the map as an occupancy grid, our robot (equipped with sonars) sees the world as a series of connected spaces. These spaces are initially mapped as an occupancy grid in a room by room fashion. As the robot leaves a space, denoted by passing through a doorway, …

Go to article

Development Approaches Coupled With Verification And Validation Methodologies For Agent-Based Mission-Level Analytical Combat Simulations, Lance E. Champagne Mar 2004

Development Approaches Coupled With Verification And Validation Methodologies For Agent-Based Mission-Level Analytical Combat Simulations, Lance E. Champagne

Theses and Dissertations

This research investigated the applicability of agent-based combat simulations to real-world combat operations. An agent-based simulation of the Allied offensive search for German U-Boats in the Bay of Biscay during World War II was constructed, extending the state-of-the-art in agent-based combat simulations, bridging the gap between the current level of agent-like combat simulations and the concept of agent-based simulations found in the broader literature. The proposed simulation advances agent-based combat simulations to “validateable” mission-level military operations. Simulation validation is a complex task with numerous, diverse techniques available and levels of validation differing significantly among simulations and applications. This research presents …

Go to article

Concurrent Cognitive Mapping And Localization Using Expectation Maximization, Kennard R. Laviers Mar 2004

Concurrent Cognitive Mapping And Localization Using Expectation Maximization, Kennard R. Laviers

Theses and Dissertations

Robot mapping remains one of the most challenging problems in robot programming. Most successful methods use some form of occupancy grid for representing a mapped region. An occupancy grid is a two dimensional array in which the array cells represents (x,y) coordinates of a cartesian map. This approach becomes problematic in mapping large environments as the map quickly becomes too large for processing and storage. Rather than storing the map as an occupancy grid, our robot (equipped with ultrasonic sonars) views the world as a series of connected spaces. These spaces are initially mapped as an occupancy grid in a …

Go to article

Analysis For Cooperative Behavior Effectiveness Of Autonomous Wide Area Search Munitions, Sang M. Park Aug 2002

Analysis For Cooperative Behavior Effectiveness Of Autonomous Wide Area Search Munitions, Sang M. Park

Theses and Dissertations

The purpose of this study is to investigate how a simulation model can accurately represent the performance of the autonomous wide area search munitions, and to find the effectiveness of the cooperative behavior on the autonomous munitions. Though it does not provide a practical solution for the development of the autonomous wide area search munitions, this research will show some meaningful allocations of the munitions tasks that are applicable to the development of the autonomous munitions. For the first phase, this thesis presents how accurately a simplified simulation model can represent a proposed weapon system by comparing the simulation results …

Go to article

Investigation Of Cooperative Behavior In Autonomous Wide Search Munitions, Robert E. Dunkel Iii Mar 2002

Investigation Of Cooperative Behavior In Autonomous Wide Search Munitions, Robert E. Dunkel Iii

Theses and Dissertations

The purpose of this research is to investigate the effectiveness of wide-area search munitions in various scenarios using different cooperative behavior algorithms. The general scenario involves multiple autonomous munitions searching for an unknown number of targets of different priority in unknown locations. Three cooperative behavior algorithms are used in each scenario: no cooperation, cooperative attack only, and cooperative classification and attack. In the cooperative cases, the munitions allocate tasks on-line as a group, using linear programming techniques to determine the optimum allocation. Each munition provides inputs to the task allocation routine in the form of probabilities of successfully being able …

Go to article

Structural Emergence And The Collaborative Behavior Of Autonomous Nano-Satellites, Daniel J. Petrovich Mar 1999

Structural Emergence And The Collaborative Behavior Of Autonomous Nano-Satellites, Daniel J. Petrovich

Theses and Dissertations

The collaborative behavior of nano-satellites in a zero-gravity environment is explored, and satellite characteristics are proposed that maximize constellation robustness and minimize manufacturing costs. Behavioral algorithms are proposed to facilitate both swarming and structural formation and are validated using the Structural Emergence Simulator (STEMS) Graphical User Interface (GUl). A payload of multiple satellites is placed in a zero-gravity environment and released to re-configure autonomously into a pre-designed structure. Data transmission between satellites is not permitted during the swarming phase of the structure formation mission. A binary behavior algorithm is invented that produces a direction and magnitude solution to the satellite …

Go to article

First Prev Next Last